Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    according to definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     historically
    0.48
     sorely
    0.44
     sucede
    0.42
     invariably
    0.40
    ዶ
    0.39
     philosoph
    0.39
     завжди
    0.39
     philosophical
    0.39
     задума
    0.39
    Historically
    0.38
    POSITIVE LOGITS
     according
    0.66
     Según
    0.66
     According
    0.65
     volgens
    0.64
    According
    0.62
     Menurut
    0.62
    according
    0.59
     podľa
    0.59
    Menurut
    0.58
     따라서
    0.58
    Act Density 0.025%

    No Known Activations